1887

n Management Dynamics : Journal of the Southern African Institute for Management Scientists - Financial distress prediction using a machine learning model : a study of JSE-listed companies

Volume 28 Number 4
  • ISSN : 1019-567X

Abstract

Timeous and accurate company financial distress prediction is becoming more important as many companies function in an ever-increasingly dynamic and globalised environment. Machine learning models allow management to consider a complex array of micro- and macro-variables in the decision-making process. This study introduces a model based on machine learning principles, combining financial, market, and macroeconomic variables in assessing the financial distress of companies listed on the Johannesburg Stock Exchange. An ensemble of principal component analysis and the support vector machine was used to develop a model with the intention of improving the accuracy of financial distress prediction. The results show an improvement in accuracy and in the ability to identify distressed companies. The contribution of this study is to emphasise to management not to limit decision-making to a one-dimensional view based only on historical financial variables, but to expand to a multi-dimensional spectrum to also include market variables and macro-economic variables.

Loading full text...

Full text loading...

Loading

Article metrics loading...

/content/journal/10520/EJC-1999428162
2019-11-01
2020-02-19

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error